| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 59688, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019832462136442838, | |
| "loss": 38.657, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019664924272885673, | |
| "loss": 31.308, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 31.739517211914062, | |
| "eval_runtime": 0.2575, | |
| "eval_samples_per_second": 194.153, | |
| "eval_steps_per_second": 7.766, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019497386409328508, | |
| "loss": 29.927, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019329848545771345, | |
| "loss": 29.1683, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 30.288894653320312, | |
| "eval_runtime": 0.2122, | |
| "eval_samples_per_second": 235.624, | |
| "eval_steps_per_second": 9.425, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019162310682214182, | |
| "loss": 28.6403, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0001899477281865702, | |
| "loss": 28.258, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 29.558307647705078, | |
| "eval_runtime": 0.2125, | |
| "eval_samples_per_second": 235.261, | |
| "eval_steps_per_second": 9.41, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018827234955099854, | |
| "loss": 27.9285, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0001865969709154269, | |
| "loss": 27.6974, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 29.129697799682617, | |
| "eval_runtime": 0.213, | |
| "eval_samples_per_second": 234.762, | |
| "eval_steps_per_second": 9.39, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00018492159227985526, | |
| "loss": 27.492, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00018324621364428363, | |
| "loss": 27.3712, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 28.81637954711914, | |
| "eval_runtime": 0.2107, | |
| "eval_samples_per_second": 237.354, | |
| "eval_steps_per_second": 9.494, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00018157083500871198, | |
| "loss": 27.204, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00017989545637314033, | |
| "loss": 27.0678, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 28.593141555786133, | |
| "eval_runtime": 0.2097, | |
| "eval_samples_per_second": 238.454, | |
| "eval_steps_per_second": 9.538, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0001782200777375687, | |
| "loss": 26.9572, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00017654469910199707, | |
| "loss": 26.8814, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 28.419679641723633, | |
| "eval_runtime": 0.2117, | |
| "eval_samples_per_second": 236.237, | |
| "eval_steps_per_second": 9.449, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00017486932046642542, | |
| "loss": 26.784, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0001731939418308538, | |
| "loss": 26.6886, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 28.238792419433594, | |
| "eval_runtime": 0.2269, | |
| "eval_samples_per_second": 220.371, | |
| "eval_steps_per_second": 8.815, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00017151856319528214, | |
| "loss": 26.6235, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0001698431845597105, | |
| "loss": 26.545, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 28.171510696411133, | |
| "eval_runtime": 0.2133, | |
| "eval_samples_per_second": 234.396, | |
| "eval_steps_per_second": 9.376, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00016816780592413886, | |
| "loss": 26.4933, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00016649242728856723, | |
| "loss": 26.4678, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 28.05875015258789, | |
| "eval_runtime": 0.2106, | |
| "eval_samples_per_second": 237.401, | |
| "eval_steps_per_second": 9.496, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00016481704865299558, | |
| "loss": 26.3908, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00016314167001742395, | |
| "loss": 26.3369, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 27.978954315185547, | |
| "eval_runtime": 0.2203, | |
| "eval_samples_per_second": 226.942, | |
| "eval_steps_per_second": 9.078, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0001614662913818523, | |
| "loss": 26.3059, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00015979091274628067, | |
| "loss": 26.2555, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 27.862077713012695, | |
| "eval_runtime": 0.2131, | |
| "eval_samples_per_second": 234.646, | |
| "eval_steps_per_second": 9.386, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00015811553411070902, | |
| "loss": 26.197, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0001564401554751374, | |
| "loss": 26.1535, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 27.81878662109375, | |
| "eval_runtime": 0.2128, | |
| "eval_samples_per_second": 234.945, | |
| "eval_steps_per_second": 9.398, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00015476477683956574, | |
| "loss": 26.1223, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0001530893982039941, | |
| "loss": 26.0879, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 27.750713348388672, | |
| "eval_runtime": 0.2338, | |
| "eval_samples_per_second": 213.838, | |
| "eval_steps_per_second": 8.554, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00015141401956842248, | |
| "loss": 26.0771, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00014973864093285083, | |
| "loss": 26.0283, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 27.70425796508789, | |
| "eval_runtime": 0.2114, | |
| "eval_samples_per_second": 236.495, | |
| "eval_steps_per_second": 9.46, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00014806326229727917, | |
| "loss": 26.0089, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00014638788366170755, | |
| "loss": 25.9742, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 27.637338638305664, | |
| "eval_runtime": 0.2146, | |
| "eval_samples_per_second": 233.03, | |
| "eval_steps_per_second": 9.321, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00014471250502613592, | |
| "loss": 25.9742, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00014303712639056427, | |
| "loss": 25.9445, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 27.6143798828125, | |
| "eval_runtime": 0.2101, | |
| "eval_samples_per_second": 237.929, | |
| "eval_steps_per_second": 9.517, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00014136174775499264, | |
| "loss": 25.9146, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.000139686369119421, | |
| "loss": 25.8983, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 27.574024200439453, | |
| "eval_runtime": 0.2119, | |
| "eval_samples_per_second": 236.006, | |
| "eval_steps_per_second": 9.44, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00013801099048384936, | |
| "loss": 25.8699, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.00013633561184827773, | |
| "loss": 25.8736, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 27.524921417236328, | |
| "eval_runtime": 0.2136, | |
| "eval_samples_per_second": 234.075, | |
| "eval_steps_per_second": 9.363, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00013466023321270608, | |
| "loss": 25.8176, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00013298485457713443, | |
| "loss": 25.8017, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 27.505229949951172, | |
| "eval_runtime": 0.2283, | |
| "eval_samples_per_second": 218.987, | |
| "eval_steps_per_second": 8.759, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0001313094759415628, | |
| "loss": 25.7503, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00012963409730599117, | |
| "loss": 25.7469, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 27.50472640991211, | |
| "eval_runtime": 0.2116, | |
| "eval_samples_per_second": 236.284, | |
| "eval_steps_per_second": 9.451, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00012795871867041952, | |
| "loss": 25.7176, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00012628334003484786, | |
| "loss": 25.6876, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_loss": 27.477006912231445, | |
| "eval_runtime": 0.215, | |
| "eval_samples_per_second": 232.548, | |
| "eval_steps_per_second": 9.302, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.00012460796139927624, | |
| "loss": 25.7203, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.0001229325827637046, | |
| "loss": 25.6757, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_loss": 27.425168991088867, | |
| "eval_runtime": 0.2125, | |
| "eval_samples_per_second": 235.312, | |
| "eval_steps_per_second": 9.412, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00012125720412813297, | |
| "loss": 25.6867, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00011958182549256132, | |
| "loss": 25.6558, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 27.394458770751953, | |
| "eval_runtime": 0.2106, | |
| "eval_samples_per_second": 237.425, | |
| "eval_steps_per_second": 9.497, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.00011790644685698968, | |
| "loss": 25.6432, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00011623106822141805, | |
| "loss": 25.6223, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_loss": 27.391796112060547, | |
| "eval_runtime": 0.2101, | |
| "eval_samples_per_second": 237.937, | |
| "eval_steps_per_second": 9.517, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00011455568958584641, | |
| "loss": 25.6129, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00011288031095027476, | |
| "loss": 25.6234, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 27.368698120117188, | |
| "eval_runtime": 0.2109, | |
| "eval_samples_per_second": 237.043, | |
| "eval_steps_per_second": 9.482, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00011120493231470313, | |
| "loss": 25.5979, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00010952955367913149, | |
| "loss": 25.623, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 27.350811004638672, | |
| "eval_runtime": 0.2251, | |
| "eval_samples_per_second": 222.106, | |
| "eval_steps_per_second": 8.884, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00010785417504355986, | |
| "loss": 25.5917, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00010617879640798821, | |
| "loss": 25.5728, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_loss": 27.310701370239258, | |
| "eval_runtime": 0.2112, | |
| "eval_samples_per_second": 236.707, | |
| "eval_steps_per_second": 9.468, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.00010450341777241657, | |
| "loss": 25.5796, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.00010282803913684493, | |
| "loss": 25.5648, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "eval_loss": 27.295310974121094, | |
| "eval_runtime": 0.217, | |
| "eval_samples_per_second": 230.466, | |
| "eval_steps_per_second": 9.219, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.0001011526605012733, | |
| "loss": 25.5587, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 9.947728186570166e-05, | |
| "loss": 25.5318, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "eval_loss": 27.264293670654297, | |
| "eval_runtime": 0.2116, | |
| "eval_samples_per_second": 236.263, | |
| "eval_steps_per_second": 9.451, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 9.780190323013e-05, | |
| "loss": 25.5344, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 9.612652459455838e-05, | |
| "loss": 25.5212, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_loss": 27.232440948486328, | |
| "eval_runtime": 0.2137, | |
| "eval_samples_per_second": 233.953, | |
| "eval_steps_per_second": 9.358, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 9.445114595898673e-05, | |
| "loss": 25.5354, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 9.27757673234151e-05, | |
| "loss": 25.5099, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "eval_loss": 27.240272521972656, | |
| "eval_runtime": 0.2111, | |
| "eval_samples_per_second": 236.859, | |
| "eval_steps_per_second": 9.474, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 9.110038868784345e-05, | |
| "loss": 25.5093, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 8.942501005227182e-05, | |
| "loss": 25.497, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_loss": 27.228918075561523, | |
| "eval_runtime": 0.2125, | |
| "eval_samples_per_second": 235.337, | |
| "eval_steps_per_second": 9.413, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 8.774963141670018e-05, | |
| "loss": 25.5092, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 8.607425278112854e-05, | |
| "loss": 25.4787, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "eval_loss": 27.228187561035156, | |
| "eval_runtime": 0.2095, | |
| "eval_samples_per_second": 238.654, | |
| "eval_steps_per_second": 9.546, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 8.439887414555691e-05, | |
| "loss": 25.4684, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 8.272349550998526e-05, | |
| "loss": 25.483, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_loss": 27.22612762451172, | |
| "eval_runtime": 0.2116, | |
| "eval_samples_per_second": 236.31, | |
| "eval_steps_per_second": 9.452, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 8.104811687441363e-05, | |
| "loss": 25.4463, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 7.937273823884198e-05, | |
| "loss": 25.4702, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "eval_loss": 27.186805725097656, | |
| "eval_runtime": 0.2143, | |
| "eval_samples_per_second": 233.331, | |
| "eval_steps_per_second": 9.333, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 7.769735960327035e-05, | |
| "loss": 25.4289, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 7.60219809676987e-05, | |
| "loss": 25.4306, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_loss": 27.194353103637695, | |
| "eval_runtime": 0.2096, | |
| "eval_samples_per_second": 238.518, | |
| "eval_steps_per_second": 9.541, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 7.434660233212707e-05, | |
| "loss": 25.4421, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 7.267122369655543e-05, | |
| "loss": 25.4518, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "eval_loss": 27.154298782348633, | |
| "eval_runtime": 0.22, | |
| "eval_samples_per_second": 227.255, | |
| "eval_steps_per_second": 9.09, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 7.099584506098379e-05, | |
| "loss": 25.4411, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 6.932046642541215e-05, | |
| "loss": 25.4264, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 27.156774520874023, | |
| "eval_runtime": 0.2232, | |
| "eval_samples_per_second": 224.006, | |
| "eval_steps_per_second": 8.96, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 6.764508778984051e-05, | |
| "loss": 25.4384, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 6.596970915426887e-05, | |
| "loss": 25.4168, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "eval_loss": 27.140100479125977, | |
| "eval_runtime": 0.2133, | |
| "eval_samples_per_second": 234.392, | |
| "eval_steps_per_second": 9.376, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 6.429433051869723e-05, | |
| "loss": 25.4029, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 6.261895188312559e-05, | |
| "loss": 25.386, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_loss": 27.135889053344727, | |
| "eval_runtime": 0.2136, | |
| "eval_samples_per_second": 234.042, | |
| "eval_steps_per_second": 9.362, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 6.0943573247553954e-05, | |
| "loss": 25.3667, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 5.926819461198231e-05, | |
| "loss": 25.3798, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "eval_loss": 27.12567138671875, | |
| "eval_runtime": 0.2109, | |
| "eval_samples_per_second": 237.075, | |
| "eval_steps_per_second": 9.483, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 5.7592815976410674e-05, | |
| "loss": 25.3643, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 5.5917437340839026e-05, | |
| "loss": 25.3643, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_loss": 27.113182067871094, | |
| "eval_runtime": 0.2121, | |
| "eval_samples_per_second": 235.709, | |
| "eval_steps_per_second": 9.428, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 5.424205870526739e-05, | |
| "loss": 25.3653, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 5.256668006969575e-05, | |
| "loss": 25.3378, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "eval_loss": 27.1131649017334, | |
| "eval_runtime": 0.2131, | |
| "eval_samples_per_second": 234.625, | |
| "eval_steps_per_second": 9.385, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 5.089130143412412e-05, | |
| "loss": 25.3598, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 4.921592279855248e-05, | |
| "loss": 25.3431, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "eval_loss": 27.10150909423828, | |
| "eval_runtime": 0.3343, | |
| "eval_samples_per_second": 149.553, | |
| "eval_steps_per_second": 5.982, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 4.754054416298084e-05, | |
| "loss": 25.3568, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 4.58651655274092e-05, | |
| "loss": 25.3384, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "eval_loss": 27.091062545776367, | |
| "eval_runtime": 0.2132, | |
| "eval_samples_per_second": 234.536, | |
| "eval_steps_per_second": 9.381, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 4.418978689183756e-05, | |
| "loss": 25.3337, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 4.251440825626592e-05, | |
| "loss": 25.3516, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "eval_loss": 27.0788631439209, | |
| "eval_runtime": 0.2156, | |
| "eval_samples_per_second": 231.865, | |
| "eval_steps_per_second": 9.275, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 4.083902962069428e-05, | |
| "loss": 25.3368, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 3.9163650985122644e-05, | |
| "loss": 25.3104, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "eval_loss": 27.085359573364258, | |
| "eval_runtime": 0.2126, | |
| "eval_samples_per_second": 235.191, | |
| "eval_steps_per_second": 9.408, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 3.7488272349551004e-05, | |
| "loss": 25.3357, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 3.581289371397936e-05, | |
| "loss": 25.3254, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "eval_loss": 27.069896697998047, | |
| "eval_runtime": 0.2134, | |
| "eval_samples_per_second": 234.3, | |
| "eval_steps_per_second": 9.372, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 3.413751507840772e-05, | |
| "loss": 25.3286, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 3.246213644283608e-05, | |
| "loss": 25.3307, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "eval_loss": 27.073589324951172, | |
| "eval_runtime": 0.2151, | |
| "eval_samples_per_second": 232.429, | |
| "eval_steps_per_second": 9.297, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 3.078675780726444e-05, | |
| "loss": 25.3197, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 2.9111379171692806e-05, | |
| "loss": 25.3153, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_loss": 27.077919006347656, | |
| "eval_runtime": 0.267, | |
| "eval_samples_per_second": 187.287, | |
| "eval_steps_per_second": 7.491, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 2.7436000536121165e-05, | |
| "loss": 25.3012, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 2.5760621900549525e-05, | |
| "loss": 25.3149, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "eval_loss": 27.066099166870117, | |
| "eval_runtime": 0.2122, | |
| "eval_samples_per_second": 235.617, | |
| "eval_steps_per_second": 9.425, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 2.4085243264977885e-05, | |
| "loss": 25.2943, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 2.2409864629406248e-05, | |
| "loss": 25.3251, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "eval_loss": 27.05815887451172, | |
| "eval_runtime": 0.2117, | |
| "eval_samples_per_second": 236.215, | |
| "eval_steps_per_second": 9.449, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 2.0734485993834608e-05, | |
| "loss": 25.2907, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 1.9059107358262967e-05, | |
| "loss": 25.3185, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "eval_loss": 27.06610107421875, | |
| "eval_runtime": 0.2143, | |
| "eval_samples_per_second": 233.359, | |
| "eval_steps_per_second": 9.334, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 1.7383728722691327e-05, | |
| "loss": 25.3016, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 1.570835008711969e-05, | |
| "loss": 25.3045, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_loss": 27.05499267578125, | |
| "eval_runtime": 0.2149, | |
| "eval_samples_per_second": 232.706, | |
| "eval_steps_per_second": 9.308, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 1.403297145154805e-05, | |
| "loss": 25.2932, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.2357592815976411e-05, | |
| "loss": 25.2952, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "eval_loss": 27.059736251831055, | |
| "eval_runtime": 0.2105, | |
| "eval_samples_per_second": 237.516, | |
| "eval_steps_per_second": 9.501, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 1.0682214180404771e-05, | |
| "loss": 25.2941, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 9.006835544833132e-06, | |
| "loss": 25.2863, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_loss": 27.0577392578125, | |
| "eval_runtime": 0.231, | |
| "eval_samples_per_second": 216.423, | |
| "eval_steps_per_second": 8.657, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 7.331456909261493e-06, | |
| "loss": 25.2943, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 5.656078273689854e-06, | |
| "loss": 25.2966, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_loss": 27.05270004272461, | |
| "eval_runtime": 0.2335, | |
| "eval_samples_per_second": 214.093, | |
| "eval_steps_per_second": 8.564, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 3.980699638118215e-06, | |
| "loss": 25.2804, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 2.3053210025465755e-06, | |
| "loss": 25.2995, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "eval_loss": 27.049020767211914, | |
| "eval_runtime": 0.2618, | |
| "eval_samples_per_second": 190.997, | |
| "eval_steps_per_second": 7.64, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 6.299423669749365e-07, | |
| "loss": 25.2862, | |
| "step": 59500 | |
| } | |
| ], | |
| "max_steps": 59688, | |
| "num_train_epochs": 3, | |
| "total_flos": 3.715405206616277e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |